Yana Diadchenko
Internship at Chulakov Studio
A service that helps copywriters quickly create content for email campaigns.
After completing a course at Chulakov Studio, I joined the studio as an intern and received the following brief:
“We need a service that can generate copy quickly. Copywriters need to work faster, especially when they have to produce multiple versions of the same message.”
To create a tool that helps copywriters quickly generate multiple versions of a text and work with them efficiently: edit, compare, and send them for approval. The workflow had to be clear and require no unnecessary clicks.
Experienced professional copywriters with clear expectations of the output they need.
The studio’s research team conducted a study and defined the following requirements:
I began by reviewing services with similar functionality, walking through their key user flows, and identifying recurring patterns.
I analyzed five services: Jasper, Anyword, Rytr, Gerwin, and Writesonic.
They all use a broadly similar layout. A navigation sidebar sits on the left, followed by a generation settings panel that usually occupies about one-third of the screen and contains the prompt and desired output parameters. The model’s responses take up most of the remaining space and can be edited or reused.
Each area scrolls independently, keeping the most important controls visible. I used this structure as the basis for my solution.
Next, I defined the visual direction for the service: its palette, typography, and overall tone—a clean, approachable interface that supports a professional and productive atmosphere.
I then created a prototype that incorporated all of the defined constraints.
I placed the chat history in the sidebar, following the pattern used by popular AI assistants such as ChatGPT and DeepSeek. The research brief required previous generations to remain readily accessible because copywriters often return to an earlier chat to update a detail such as a date or holiday name. The sidebar can be collapsed while the user works in the main area, and chat search makes previous conversations easier to find.
I divided the generation settings into four areas: the prompt, channel, target audience, and number of versions.
The prompt is the foundation of the request. Without clear instructions, the model cannot produce the intended result. A 1,000-character limit encourages users to be specific.
SMS, push notifications, and email are the channels used by the service’s target audience. The selected channel determines the length and format of the copy: an SMS may be a single sentence, while an email can be a full paragraph.
I made the channel tabs larger and more prominent because channel is one of the two required settings and generation cannot start until it is selected.
The target audience section includes three parameters: gender, age, and psychographic profile. Together, they shape the tone of voice, vocabulary, and message for a particular reader. The psychographic profile also affects the emotional tone and presentation style.
One version is generated by default, with a maximum of ten to manage model load. This is usually sufficient, but users can run generation again to add more versions to the existing results.
Alongside the generated results, the workspace includes a “Send for approval” button. Selected texts are sent to an editor for review, as required by the brief. Each response can be edited, copied, or shared, and unnecessary versions can be collapsed when the list becomes too long.
I added required-field indicators and validation errors for the prompt and channel fields.
The Generate button remains disabled until all required fields are complete. Clear guidance and validation help users understand what is missing, correct errors, and reach a successful result.
I added a question-mark icon that opens prompt-writing guidance. Not every professional copywriter is familiar with AI assistants, so some may need help creating an effective prompt.
I placed model responses on separate surfaces to improve readability. Without clear separation, a long list of responses can become a wall of text and increase cognitive load.
I refined the visual hierarchy within the response cards. I made the checkboxes larger and easier to select, while reducing the response titles so they would not compete with the section heading.
I moved the response controls to the top and revealed them on hover, reducing visual noise from repeated elements.
I displayed multi-select values as chips to make selected items easier to scan and remove with a single click.
I changed the new-chat icon. Participants in the hallway usability test did not immediately understand the pencil icon, while they recognized the plus icon straight away.
After the final revisions, I completed the visual design, defined the color palette, and assembled a UI kit. I also documented detailed flows for creating and finding chats and editing text, then presented the solution to the team.
I managed to fit all essential information into a single workspace, so users do not have to switch between tabs.
The project received positive feedback. I gained valuable experience, collected useful insights, and became even more engaged with the design process.
Unless expressly stated otherwise, the texts, structure and design of the site, graphics, illustrations, images and other materials created by me are subject to copyright.
Copying, reproduction, modification, publication, distribution, placement on other resources and other use of these materials for commercial or non-commercial purposes without prior written permission is not allowed.
Trademarks, logos, company names and materials of third parties belong to the respective copyright holders and are presented on the site exclusively as part of a portfolio.